* Added ERROR message class to handle fatal error messages.
New ERROR message class will print the message in all debug level,
including none.
Change some of the fatal error message to be in ERROR instead of WARN.
Added new error handler function to print out more meaningful error
message in the future.
* Added CHANGELOG entry.
* Update CHANGELOG.md
Co-authored-by: Jeffrey Novotny <jnovotny@amd.com>
* Change to no longer reuse NONE as ERROR. ERROR is now a separated class.
* Update CHANGELOG.md
Co-authored-by: Jeffrey Novotny <jnovotny@amd.com>
---------
Co-authored-by: Jeffrey Novotny <jnovotny@amd.com>
[ROCm/rccl commit: 1ce83d5cc0]
* Added ERROR message class to handle fatal error messages.
New ERROR message class will print the message in all debug level,
including none.
Change some of the fatal error message to be in ERROR instead of WARN.
Added new error handler function to print out more meaningful error
message in the future.
* Added CHANGELOG entry.
* Update CHANGELOG.md
Co-authored-by: Jeffrey Novotny <jnovotny@amd.com>
* Change to no longer reuse NONE as ERROR. ERROR is now a separated class.
* Update CHANGELOG.md
Co-authored-by: Jeffrey Novotny <jnovotny@amd.com>
---------
Co-authored-by: Jeffrey Novotny <jnovotny@amd.com>
* fix crash created by path and arg for pc_sampling and add copyright for mat_mul
* resolve fomat issue of line too long
* bugfixes
* copy gfx9 config template to analysis config in src
---------
Co-authored-by: Wang <ywang103@ctr2-alola-login-01.amd.com>
Co-authored-by: Vignesh Edithal <Vignesh.Edithal@amd.com>
* prevent batching when send/recv bytes dont match, restore bit reversal for channel to part mapping, prevent batching beyond 32-nodes
* correct computation for channel to part mapping
* update changelog
* disabling p2p-batching by default
[ROCm/rccl commit: 641c0eb51c]
* prevent batching when send/recv bytes dont match, restore bit reversal for channel to part mapping, prevent batching beyond 32-nodes
* correct computation for channel to part mapping
* update changelog
* disabling p2p-batching by default
Allow amdsmi to find libamd_smi.so and librocm-core.so relative to
amdsmi_wrapper.py location.
The amdsmi_wrapper.py file is located in
_rocm_sdk_core/share/amd_smi/amdsmi and the libraries are in
_rocm_sdk_core/lib/libamd_smi.so.26.
_rocm_sdk_core/lib/librocm-core.so.1.
Allow amdsmi to find libamd_smi.so and librocm-core.so relative to
amdsmi_wrapper.py location.
The amdsmi_wrapper.py file is located in
_rocm_sdk_core/share/amd_smi/amdsmi and the libraries are in
_rocm_sdk_core/lib/libamd_smi.so.26.
_rocm_sdk_core/lib/librocm-core.so.1.
[ROCm/amdsmi commit: ad20d57162]
To make the functional tests more useful for benchmarking, allow user to
specify the number of loops and related parameters via command options.
Signed-off-by: Allen Hubbe <allen.hubbe@amd.com>
[ROCm/rocshmem commit: ed91c8cce2]
To make the functional tests more useful for benchmarking, allow user to
specify the number of loops and related parameters via command options.
Signed-off-by: Allen Hubbe <allen.hubbe@amd.com>
The out of bound writes caused corruption in next field,
which was weight. Fixed by reading to a temp and then assigning
safely.
Signed-off-by: Bindhiya Kanangot Balakrishnan <Bindhiya.KanangotBalakrishnan@amd.com>
The out of bound writes caused corruption in next field,
which was weight. Fixed by reading to a temp and then assigning
safely.
Signed-off-by: Bindhiya Kanangot Balakrishnan <Bindhiya.KanangotBalakrishnan@amd.com>
[ROCm/amdsmi commit: a2aae5e8a9]
* Add initial commit to increase tb size to 512
* Fix LL perf issue when subset of NCCL_MAX_NTHREADS is used
Adding a constant to barrier_generic logic from using fallback logic when nthreads < NCCL_MAX_NTHREADS and nthreads == blockDim.X
* Adjust nthreads for LL
* Opt threads for reduce_scatter upper small range
* Add macro for single node
* Restrict MSCCL to 256 threads to prevent mem access fault
* Support pre-MI350 compatibility
* Partially refactor threadblock size override
* Use const macros instead of numerals
* opt out of unused function
[ROCm/rccl commit: 12f51ba8bf]
* Add initial commit to increase tb size to 512
* Fix LL perf issue when subset of NCCL_MAX_NTHREADS is used
Adding a constant to barrier_generic logic from using fallback logic when nthreads < NCCL_MAX_NTHREADS and nthreads == blockDim.X
* Adjust nthreads for LL
* Opt threads for reduce_scatter upper small range
* Add macro for single node
* Restrict MSCCL to 256 threads to prevent mem access fault
* Support pre-MI350 compatibility
* Partially refactor threadblock size override
* Use const macros instead of numerals
* opt out of unused function
Added json and csv output format support for newly
added xgmi link_status. Aligned legend.
Signed-off-by: Bindhiya Kanangot Balakrishnan <Bindhiya.KanangotBalakrishnan@amd.com>
David DeBonis
Yiltan
Yiannis Papadopoulos
Kian Cossettini
Ioannis Assiouras
Arm Patinyasakdikul
ywang103-amd
gabrpham_amdeng
adapryor
isaki001
Dmitrii
Galantsev, Dmitrii
Allen Hubbe
Bindhiya Kanangot Balakrishnan
Bertan Dogancay
marandje
Nilesh M Negi
Mustafa Abduljabbar
Charis Poag
Allan Xavier
gilbertlee-amd
cadolphe-amd